Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2888 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1730. Min Act: -0.0001

Data Index: 141062 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1741. Min Act: -0.0001

Data Index: 718584 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1602. Min Act: -0.0001

Data Index: 407304 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1657. Min Act: -0.0001

Data Index: 584348 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1537. Min Act: -0.0001

Data Index: 467167 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1074928 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1552. Min Act: -0.0001

Data Index: 112483 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1327637 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1378. Min Act: -0.0001

Data Index: 172432 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1315. Min Act: -0.0001

Data Index: 681162 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1414. Min Act: -0.0001

Data Index: 508807 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1318625 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1354. Min Act: -0.0000

Data Index: 241441 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1153694 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1316. Min Act: -0.0001

Data Index: 258308 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1419. Min Act: -0.0001

Data Index: 822081 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1283. Min Act: -0.0001

Data Index: 265988 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1390. Min Act: -0.0001

Data Index: 214215 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1277. Min Act: -0.0001

Data Index: 714407 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1272. Min Act: -0.0001

Data Index: 921492 (C4 (Web Text))

Max Activating Token Index: 637